An intelligent processing control method and system for granulation of oyster peptide health products

Abstract

The present invention discloses an intelligent processing control method and system for the production and granulation of oyster peptide health products, which relates to the field of intelligent manufacturing technology of health products, including real-time detection of environmental parameters by environmental sensors, identification of environmental parameter change values ​​by support vector regression SVR, and dynamic adjustment of the formula ratio of oyster peptide health products by using preset formula adjustment rules; according to the adjusted formula ratio, the weighed raw materials are evenly mixed and sent to a granulator, the working parameters of the granulator are preliminarily adjusted according to the raw material data, and initial particles are made; the initial particle characteristics are extracted using a deep learning model, the quality index of the particles is calculated, the working parameters of the granulator are adjusted according to the quality index of the particles, and the quality of the initial particles is optimized; the initial humidity of the particles after monitoring and optimization is selected by the central control system according to the initial humidity data. The present invention optimizes the granulation and drying processes by dynamically adjusting the formula ratio, thereby improving product quality and production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing of health products, and in particular to an intelligent processing control method and system for the production and granulation of oyster peptide health products. Background Art

[0002] In recent years, with the rapid development of the food and health care products industry, the requirements for product quality and production efficiency have been continuously improved. As a functional health care product rich in various amino acids and trace elements, the granulation process of oyster peptides is particularly critical. The traditional granulation process mainly relies on manual experience and fixed parameters, which is difficult to cope with the dynamic changes in the production environment, resulting in unstable product quality. With the continuous development of the Internet of Things (IoT), artificial intelligence (AI) and big data technologies, the application of intelligent production control systems has gradually become possible. These technologies can not only monitor production environment parameters in real time, but also perform data analysis and prediction through advanced algorithm models, thereby realizing intelligent control of the production process. For example, machine learning algorithms such as support vector regression (SVR) and convolutional neural networks (CNN) have shown strong application potential in environmental parameter identification and particle quality assessment.

[0003] Although the existing production control system has improved production efficiency and product quality to a certain extent, there are still many shortcomings. First, the traditional environmental monitoring and formula adjustment methods mainly rely on manual experience, resulting in poor accuracy and timeliness of formula adjustment. Secondly, the working parameter adjustment of the granulator is usually based on fixed process parameters, which cannot dynamically adapt to the characteristics of raw materials and environmental changes, and easily leads to fluctuations in particle quality. In addition, the existing particle quality detection methods mostly rely on manual visual inspection and manual measurement, which are inefficient and easily affected by subjective factors. Finally, the existing humidity monitoring and drying mode selection methods are mostly static settings, and the drying parameters cannot be dynamically adjusted according to the actual humidity of the particles, resulting in inconsistent drying effects. These problems not only affect the quality of the final product, but also increase production costs and time. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent processing control method and system for the production of oyster peptide health products granulation to solve the problems of inflexible granulator parameter adjustment, low particle quality detection efficiency and inconsistent drying effect in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an intelligent processing control method for the production and granulation of oyster peptide health products, which includes: detecting environmental parameters in real time through environmental sensors, using support vector regression SVR to identify the change values ​​of environmental parameters, and using preset formula adjustment rules to dynamically adjust the formula ratio of oyster peptide health products; according to the adjusted formula ratio, the weighed raw materials are evenly mixed and sent to a granulator, the working parameters of the granulator are preliminarily adjusted according to the raw material data, and initial particles are prepared; the initial particle characteristics are extracted using a deep learning model, the quality indicators of the particles are calculated, the working parameters of the granulator are adjusted according to the quality indicators of the particles, and the quality of the initial particles is optimized; the initial humidity data of the optimized particles is monitored, and the central control system dynamically selects the drying mode according to the initial humidity data, so that the selected drying mode instruction is sent to the drying equipment, the drying process is started, and the moisture in the optimized particles is removed; the dried particles are packaged, and a quality report of the oyster peptide health products is generated.

[0008] As a preferred solution of the intelligent processing control method for the production of oyster peptide health products of the present invention, wherein: the environmental parameters are detected in real time by environmental sensors, support vector regression SVR is used to identify the change value of the environmental parameters, and the formula ratio of the oyster peptide health products is dynamically adjusted according to the initial formula adjustment rules. The specific steps are as follows:

[0009] Deploy high-precision temperature sensors and humidity sensors at the production site to collect environmental parameters in real time, including temperature data and humidity data;

[0010] The environmental parameters are transmitted to the central control system through IoT, and the central control system uses SVR to identify the change value of the environmental parameters;

[0011] Based on the change value of environmental parameters, the preset formula adjustment rules are used to dynamically adjust the formula ratio of oyster peptide health products. The expression is:

[0012]

[0013] Among them, NR is the adjusted formula ratio, BR is the base formula ratio, k is the formula adjustment coefficient, ΔT h is the ambient temperature change, T h is the ambient temperature reference value, ΔH h is the change in ambient humidity, H h It is the reference value of ambient humidity.

[0014] As a preferred solution of the intelligent processing control method for the production of oyster peptide health products of the present invention, wherein: according to the adjusted formula ratio, the weighed raw materials are evenly mixed and sent to the granulator, the working parameters of the granulator are preliminarily adjusted according to the raw material data, and the initial granules are prepared, and the specific steps are as follows:

[0015] The adjusted formula ratio NR is transmitted to the batching system through the Internet of Things. The batching system accurately weighs the raw materials according to the adjusted formula, and sends the weighed raw materials to the mixer for uniform mixing and then to the granulator;

[0016] The raw material data is monitored in real time through the sensors on the granulator, and transmitted to the central control system through IoT; the raw material data includes: raw material temperature and raw material humidity;

[0017] The central control system evaluates the influence of raw material data on particle production by quantifying the deviation of data relative to the reference value, which is expressed as:

[0018]

[0019] Among them, E is the influence of raw material data on particle production, T m is the raw material temperature, T r is the raw material temperature reference value, H m is the raw material humidity, H r It is the reference value of raw material humidity;

[0020] Define an environmental impact threshold E based on historical data and process requirements td , according to the influence degree E of raw material data on granule production, preliminarily adjust the working parameters of the granulator;

[0021] When E≤E td When the temperature and humidity of the raw materials affect the pellet production, it means that the influence of the current raw material temperature and humidity data on the pellet production is within the safe range, and there is no need to adjust the working parameters of the pelletizer.

[0022] When E>E td When the temperature and humidity of the current raw materials affect the pellet production beyond the safe range, the working parameters of the pellet mill need to be adjusted. The working parameters of the pellet mill include: the pressure, speed, heating intensity and shear force applied by the pellet mill.

[0023] The granulator performs preliminary granulation according to the adjusted working parameters to form initial granules.

[0024] As a preferred solution of the intelligent processing control method for the production of oyster peptide health products of the present invention, wherein: the initial particle characteristics are extracted by using a deep learning model and the quality index of the particles is calculated, and the specific steps are as follows:

[0025] The high-resolution camera on the pelletizer collects the image data of the initial pellets in real time and transmits the image data to the central control system through IoT technology;

[0026] The central control system uses the input layer of the deep learning model to receive the image data of the initial particles, and extracts the particle features through the convolution layer. The particle features are reduced in feature dimension through the pooling layer, and then the global particle features are integrated through the fully connected layer, and Dropout is used to prevent overfitting. The deep learning model includes the input layer, convolution layer, pooling layer and fully connected layer.

[0027] Particle characteristics include: average particle size, regularity of shape, and degree of surface defects;

[0028] Based on the particle features extracted by the deep learning model, the quality evaluation index of the particles is calculated, and the expression is:

[0029]

[0030] Where S represents the average size of the particles, S i represents the ideal particle size, λ1 is the particle size difference adjustment factor, D(S) represents the regularity of particle shape, λ2 is the particle shape regularity adjustment factor, F(S) represents the degree of particle surface defects, λ3 is the particle surface defect adjustment factor, and Q is the particle quality index.

[0031] As a preferred solution of the intelligent processing control method for the production of oyster peptide health products of the present invention, wherein: the working parameters of the granulator are adjusted according to the quality index of the particles, and the quality of the initial particles is optimized, and the specific steps are as follows:

[0032] Define a particle quality standard threshold Q based on historical data and process requirements th , according to the quality index Q of the particles, adjust the working parameters of the granulator again;

[0033] When Q ≥ Q th When , the current particle quality is considered qualified;

[0034] When Q < Q th When , the current particle quality is considered unqualified;

[0035] When the particle quality is unqualified, calculate the particle quality index Q and the particle quality standard threshold Q th According to the calculated difference, the working parameters of the granulator are adjusted again;

[0036] The pelletizer optimizes the quality of the initial pellets according to the latest operating parameters.

[0037] As a preferred solution of the intelligent processing control method for the production of oyster peptide health products of the present invention, wherein: the initial humidity data of the particles after monitoring optimization, the central control system dynamically selects the drying mode according to the initial humidity data, and the specific steps are as follows:

[0038] The high-precision humidity sensor at the exit of the granulator monitors the initial humidity data of the optimized granules in real time, and transmits the initial humidity data collected by the humidity sensor to the central control system through IoT technology;

[0039] The central control system calculates the deviation between the initial humidity data of the optimized particles and the humidity of the particles in the production standard according to the received initial humidity data;

[0040] According to the deviation value H between the initial humidity data of the optimized particles and the humidity of the particles in the production standard dev , dynamically select the drying mode; the drying modes include: primary drying, secondary drying and tertiary drying;

[0041] Based on historical data and process requirements, a low humidity deviation threshold H is defined. low and high humidity deviation threshold H high ;

[0042] When H dev ≤H low When drying, select the first-level drying mode;

[0043] When H low <H dev ≤H high When the air is in the hot zone, select the secondary drying mode;

[0044] When H dev >H high When drying, select the three-level drying mode;

[0045] The central control system sends the selected drying mode command to the drying equipment, starting the drying process to remove moisture from the optimized particles.

[0046] As a preferred solution of the intelligent processing control method for the production of oyster peptide health products according to the present invention, the dried particles are packaged and a quality report of the oyster peptide health products is generated. The specific steps are as follows:

[0047] After the drying process is completed, the dried particles are transferred from the drying equipment to the packaging area by a conveyor belt;

[0048] In the packaging area, high-precision weighing equipment is used to weigh the dried particles, and an automatic packaging machine is used to seal and package the weighed particles;

[0049] After packaging is completed, the central control system records the quality indicators of the current batch of particles, and generates a quality report for the current batch of oyster peptide health products based on the quality indicators of the current batch.

[0050] In the second aspect, the present invention provides an intelligent processing control system for the production and granulation of oyster peptide health products, including an environmental parameter monitoring and formula adjustment module, a preliminary adjustment module for granulator parameters, an initial particle quality optimization module, a particle drying module, and a particle packaging and quality report generation module; the environmental parameter monitoring and formula adjustment module is used to detect environmental parameters in real time through environmental sensors, use SVR to identify environmental parameter change values, and use preset formula adjustment rules to dynamically adjust the formula ratio of oyster peptide health products; the preliminary adjustment module for granulator parameters is used to evenly mix the weighed raw materials and feed them into the granulator according to the adjusted formula ratio, preliminarily adjust the working parameters of the granulator according to the raw material data, and prepare initial particles; the initial particle quality optimization module is used to extract the initial particle characteristics using a deep learning model, calculate the quality index of the particles, adjust the working parameters of the granulator according to the quality index of the particles, and optimize the quality of the initial particles; the particle drying module is used to monitor the initial humidity of the optimized particles, and the central control system dynamically selects the drying mode according to the initial humidity data; the particle packaging and quality report generation module is used to package the dried particles and generate an oyster peptide health product quality report.

[0051] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent processing control method for the production and granulation of oyster peptide health products as described in the first aspect of the present invention is implemented.

[0052] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the intelligent processing control method for the production and granulation of oyster peptide health products as described in the first aspect of the present invention is implemented.

[0053] The beneficial effects of the present invention are as follows: by real-time monitoring of environmental parameters and dynamic adjustment of formula ratios by SVR, the accuracy and timeliness of the formula are ensured, and the stability and consistency of the product are improved; by uniform mixing of raw materials and preliminary adjustment of granulator parameters, the efficiency of granule production and the initial quality of the granules are ensured; by using a deep learning model to extract granule features and optimize granulator parameters, the quality and consistency of the granules are further improved; by real-time monitoring of initial humidity and dynamic selection of drying modes, the efficiency of the drying process and the quality stability of the dried granules are ensured. Ultimately, the present invention improves the production efficiency and product quality of oyster peptide health products, reduces production costs, and enhances the market competitiveness of products. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0055] Figure 1 This is a flow chart of the intelligent processing control method for the production and granulation of oyster peptide health products in Example 1.

[0056] Figure 2 This is a flow chart of the intelligent processing control system for the production and granulation of oyster peptide health products in Example 1. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an intelligent processing control method for granulation of oyster peptide health products, comprising the following steps:

[0061] S1. Real-time detection of environmental parameters through environmental sensors, use of support vector regression (SVR) to identify the change values ​​of environmental parameters, and use of preset formula adjustment rules to dynamically adjust the formula ratio of oyster peptide health products.

[0062] Furthermore, high-precision temperature sensors and humidity sensors are deployed at the production site to collect environmental parameters in real time, including temperature data and humidity data.

[0063] Environmental parameters are transmitted to the central control system through IoT, and the central control system uses support vector regression SVR to identify the change value of environmental parameters; for example: assuming that the temperature gradually rises in a certain period of time, the SVR model will predict the temperature change value in the future period of time based on historical data and current data, and dynamically adjust the formula ratio of oyster peptide health products accordingly to ensure the stability of the production process and product quality. In this way, the central control system can respond to environmental changes in real time, adjust production parameters in a timely manner, and improve the intelligence level of the production process and product quality.

[0064] Based on the change value of environmental parameters, the preset formula adjustment rules are used to dynamically adjust the formula ratio of oyster peptide health products. The expression is:

[0065]

[0066] Among them, NR is the adjusted formula ratio, BR is the base formula ratio, k is the formula adjustment coefficient, ΔT h is the ambient temperature change, T h is the ambient temperature reference value, ΔH h is the change in ambient humidity, H h It is the reference value of ambient humidity.

[0067] It should be noted that the preset formula adjustment rules are formulated based on historical data, experimental data and process experience. By analyzing the environmental parameters and formula ratio data accumulated in the past production process, the optimal formula ratio adjustment strategy under different environmental conditions is summarized to ensure the stability of the production process and product quality.

[0068] Through the preset formula adjustment rules and combined with the change values ​​of environmental parameters, the ratio of the ingredients in the formula of oyster peptide health products can be adjusted to ensure the stability of the production process and the high quality of the final product.

[0069] S2. According to the adjusted formula ratio, the weighed raw materials are evenly mixed and sent to the granulator, the working parameters of the granulator are preliminarily adjusted according to the raw material data, and initial granules are produced.

[0070] Furthermore, the adjusted formula ratio NR is transmitted to the batching system through the Internet of Things. The batching system accurately weighs the raw materials according to the adjusted formula, and sends the weighed raw materials to the mixer for uniform mixing and then to the granulator.

[0071] The raw material data is monitored in real time through the sensors on the granulator, and transmitted to the central control system through IoT; the raw material data includes: raw material temperature and raw material humidity;

[0072] The central control system evaluates the influence of raw material data on particle production by quantifying the deviation of data relative to the reference value, which is expressed as:

[0073]

[0074] Among them, E is the influence of raw material data on particle production, T m is the raw material temperature, T r is the raw material temperature reference value, H m is the raw material humidity, H r It is the reference value of raw material humidity.

[0075] It should be noted that by calculating the raw material temperature T m and raw material temperature reference value T r The relative deviation between the raw material humidity H m And raw material humidity reference value H r The relative deviation between the two relative deviations is calculated, and then the square root of the sum of the squares of the two relative deviations is taken to obtain a comprehensive degree of influence of the raw material data on the pellet production. This calculation method can quantify the deviation of temperature and humidity into a single value, thereby comprehensively evaluating the degree of influence of the raw material data on the pellet production. In this way, the central control system can more accurately determine whether the current raw material conditions are suitable for pelleting, and then preliminarily adjust the working parameters of the pellet mill to ensure the stability of pellet production and the consistency of pellet quality.

[0076] Define an environmental impact threshold E based on historical data and process requirements td , according to the influence degree E of raw material data on particle production, preliminarily adjust the working parameters of the granulator.

[0077] When E≤E td When the temperature and humidity of the raw materials affect the pellet production, it means that the influence of the current raw material temperature and humidity data on the pellet production is within the safe range, and there is no need to adjust the working parameters of the pelletizer.

[0078] When E>E td , it means that the current temperature and humidity data of the raw materials have an impact on the pellet production beyond the safe range, and the working parameters of the pelletizer need to be adjusted; the working parameters of the pelletizer include: the pressure, speed, heating intensity and shear force applied by the pelletizer; specifically, if the temperature or humidity of the raw materials is high, it may cause the raw materials to become too viscous or the fluidity to deteriorate. At this time, it is necessary to increase the pressure of the pelletizer or adjust other related parameters to ensure the quality and consistency of pellet formation.

[0079] The granulator performs preliminary granulation according to the adjusted working parameters to form initial granules.

[0080] It should also be noted that the oyster peptide health product is produced by mixing 110mg oyster peptide powder, 110mg maca powder, 110mg Cistanche powder, 100mg sorbitol, 100mg xylitol, 100mg D-mannitol, 20mg ginseng freeze-dried powder, 20mg dami grass leaves, 20mg cornus officinalis, 20mg eucommia leaf powder, 20mg polygonatum powder, 20mg cordyceps militaris, 3mg sea cucumber peptide, 3mg yeast extract, 3mg lycopene, 3mg edible flavoring, and 8mg magnesium stearate.

[0081] S3. Use the deep learning model to extract the initial particle features, calculate the quality index of the particles, adjust the working parameters of the pelletizer according to the quality index of the particles, and optimize the quality of the initial particles.

[0082] Furthermore, the image data of the initial particles is collected in real time by a high-resolution camera on the granulator, and the image data is transmitted to the central control system through IoT technology.

[0083] The central control system uses the input layer of the deep learning model to receive the image data of the initial particles, and extracts the particle features through the convolution layer. The particle features are reduced in feature dimension through the pooling layer, and then the global particle features are integrated through the fully connected layer, and Dropout is used to prevent overfitting. The deep learning model includes the input layer, convolution layer, pooling layer and fully connected layer.

[0084] Particle characteristics include: average particle size, regularity of shape and degree of surface defects.

[0085] Based on the particle features extracted by the deep learning model, the quality index of the particles is calculated, and the expression is:

[0086]

[0087] Where S represents the average size of the particles, S i represents the ideal particle size, λ1 is the particle size difference adjustment factor, D(S) represents the regularity of particle shape, λ2 is the particle shape regularity adjustment factor, F(S) represents the degree of particle surface defects, λ3 is the particle surface defect adjustment factor, and Q is the particle quality index.

[0088] It should be noted that the particle shape regularity D(S) is calculated by analyzing the geometric features in the particle image, and the expression is:

[0089]

[0090] Where A is the total area of ​​the particle, P is the perimeter of the particle, and A c is the area of ​​the smallest enclosing circle of the particle, σ a is the standard deviation of the particle aspect ratio, is the standard deviation of the ideal particle aspect ratio, w1 represents the weight coefficient of the particle arc, w2 represents the weight coefficient of the particle shape, and w3 represents the weight coefficient of the particle aspect ratio;

[0091] The particle surface defect degree F(S) is calculated by analyzing the surface features in the particle image, and the expression is:

[0092]

[0093] Where A is the total area of ​​the particle, A d is the area of ​​defective region on the particle surface, d g is the depth of the g-th defect, n is the number of defects, A s is the area of ​​the smooth area on the particle surface, η1 is the weight coefficient of the proportion of the defective area on the particle surface to the total area, η2 is the weight coefficient of the sum of the square of the defect depth on the particle surface to the total area, and η3 is the weight coefficient of the proportion of the smooth area on the particle surface to the total area;

[0094] Define a particle quality standard threshold Q based on historical data and process requirements th , according to the quality index Q of the particles, adjust the working parameters of the granulator again.

[0095] When Q ≥ Q th When , the current particle quality is considered qualified.

[0096] When Q < Q th When , the current particle quality is considered unqualified.

[0097] When the particle quality is unqualified, calculate the particle quality index Q and the particle quality standard threshold Q th According to the calculated difference, the working parameters of the granulator are adjusted again.

[0098] For example, the particle quality index Q value is 0.65, the quality standard threshold Qth is 0.7, and the difference is 0.7-0.65=0.05. If the current pressure P old is 100MPa, and the adjustment coefficient μ1 is 0.1, then the new pressure P new For: P new =100+0.1·0.05=100.005MPa.

[0099] The pelletizer optimizes the quality of the initial pellets according to the latest operating parameters.

[0100] It should also be noted that by using a deep learning model to extract particle features and calculate quality indicators, the central control system can evaluate the quality of the particles in real time and adjust the working parameters of the pelletizer again to optimize the particle quality. This step significantly improves the quality and consistency of particle formation, reduces the generation of unqualified products, and improves production efficiency and the market competitiveness of the final product.

[0101] S4. Monitor the initial humidity data of the optimized particles. The central control system dynamically selects a drying mode according to the initial humidity data, so that the selected drying mode instruction is sent to the drying equipment to start the drying process and remove moisture from the optimized particles.

[0102] Furthermore, the initial humidity data of the optimized granules is monitored in real time through a high-precision humidity sensor at the granulator outlet, and the initial humidity data collected by the humidity sensor is transmitted to the central control system through IoT technology.

[0103] The central control system calculates the deviation between the initial humidity data of the optimized particles and the humidity of the particles in the production standard based on the received initial humidity data.

[0104] According to the deviation value H between the initial humidity data of the optimized particles and the humidity of the particles in the production standard dev , dynamically select the drying mode; the drying modes include: primary drying, secondary drying and tertiary drying.

[0105] Based on historical data and process requirements, a low humidity deviation threshold H is defined. low and high humidity deviation threshold H high .

[0106] When H dev ≤H low When drying, select the first level drying mode.

[0107] When H low <H dev ≤H high Select the secondary drying mode.

[0108] When H dev >H high , select the three-level drying mode.

[0109] It should be noted that the first-level drying mode is a mild drying method, which is suitable for situations where the initial humidity of the particles deviates slightly from the ideal humidity. The drying temperature in this mode is low and the drying time is long, which can slowly and evenly remove the moisture in the particles, avoiding surface hardening and internal moisture residue caused by rapid drying; the second-level drying mode is a medium-intensity drying method, which is suitable for situations where the initial humidity of the particles deviates moderately from the ideal humidity. The drying temperature and time in this mode are between the first and third levels, which can effectively remove most of the moisture in a short time while maintaining the structural integrity of the particles; the third-level drying mode is a high-intensity drying method, which is suitable for situations where the initial humidity of the particles deviates greatly from the ideal humidity. The drying temperature in this mode is high and the drying time is short, which can quickly remove a large amount of moisture in the particles, but it is necessary to pay attention to controlling the temperature and time to avoid overheating that causes particle deterioration or structural damage.

[0110] The central control system sends the selected drying mode command to the drying equipment, starting the drying process to remove moisture from the optimized particles.

[0111] It should also be noted that by dynamically selecting the appropriate drying mode, the central control system can accurately select the most appropriate drying method based on the actual moisture deviation of the particles, ensuring the efficiency of the drying process and the final quality of the particles, avoiding particle quality problems caused by improper humidity control, thereby improving production efficiency and product consistency.

[0112] S5. Package the dried particles and generate a quality report for the oyster peptide health product.

[0113] Furthermore, after the drying process is completed, the dried particles are transported from the drying equipment to the packaging area via a conveyor belt.

[0114] In the packaging area, high-precision weighing equipment is used to weigh the dried particles, and an automated packaging machine is used to seal and package the weighed particles.

[0115] After packaging is completed, the central control system records the quality indicators of the current batch of particles, and generates a quality report for the current batch of oyster peptide health products based on the quality indicators of the current batch.

[0116] It should be noted that the dried particles are transported to the packaging area by a conveyor belt, and are weighed and sealed using high-precision weighing equipment and automated packaging machines. The central control system records and generates a quality report for the current batch of oyster peptide health products. This process significantly improves production efficiency, ensures the high quality and consistency of each batch of products, enhances product traceability, and improves production efficiency and product quality stability.

[0117] This embodiment also provides an intelligent processing control system for the production of oyster peptide health products, including: an environmental parameter monitoring and formula adjustment module, a granulator parameter preliminary adjustment module, an initial granule quality optimization module, a granule drying module, and a granule packaging and quality report generation module;

[0118] Environmental parameter monitoring and formula adjustment module: used to detect environmental parameters in real time through environmental sensors, use SVR to identify environmental parameter change values, and use preset formula adjustment rules to dynamically adjust the formula ratio of oyster peptide health products;

[0119] Granulator parameter preliminary adjustment module: used to evenly mix the weighed raw materials according to the adjusted formula ratio and send them to the granulator, preliminarily adjust the granulator's working parameters according to the raw material data, and make initial granules;

[0120] Initial particle quality optimization module: used to extract initial particle features using a deep learning model, calculate the quality index of the particles, adjust the working parameters of the pelletizer according to the quality index of the particles, and optimize the quality of the initial particles;

[0121] Granule drying module: used to monitor the initial humidity of the optimized granules. The central control system dynamically selects the drying mode based on the initial humidity data.

[0122] Granule packaging and quality report generation module: used to package the dried granules and generate the oyster peptide health product quality report.

[0123] This embodiment also provides a computer device, which is suitable for the intelligent processing control method for the production and granulation of oyster peptide health products, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the intelligent processing control method for the production and granulation of oyster peptide health products proposed in the above embodiment.

[0124] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0125] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the intelligent processing control method for granulation of oyster peptide health products production proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0126] In summary, the present invention ensures the accuracy and timeliness of the formula and improves the stability and consistency of the product through real-time monitoring of environmental parameters and dynamic adjustment of the formula ratio by SVR; ensures the efficiency of granule production and the initial quality of the granules through uniform mixing of raw materials and preliminary adjustment of granulator parameters; further improves the quality and consistency of the granules by extracting granule features and optimizing granulator parameters using a deep learning model; ensures the efficiency of the drying process and the quality stability of the dried granules through real-time monitoring of initial humidity and dynamic selection of drying mode. Finally, the present invention improves the production efficiency and product quality of oyster peptide health products, reduces production costs, and enhances the market competitiveness of products.

[0127] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the intelligent processing control method for the production of oyster peptide health products granulation are provided.

[0128] Before the experiment, all equipment was calibrated to ensure the accuracy of the data. The ingredients of the oyster peptide health supplement used in the experiment include: 110mg oyster peptide powder, 110mg maca powder, 110mg Cistanche powder, 100mg sorbitol, 100mg xylitol, 100mg D-mannitol, 20mg ginseng freeze-dried powder, 20mg Da Mi grass leaves, 20mg Cornus officinalis, 20mg Eucommia leaf powder, 20mg Polygonatum powder, 20mg Cordyceps militaris, 3mg sea cucumber peptide, 3mg yeast extract, 3mg lycopene, 3mg edible flavor, 8mg magnesium stearate, and the environmental parameters, granulator working parameters, granule quality indicators and drying mode of each stage were recorded in detail for subsequent analysis and comparison.

[0129] The experiment is divided into four stages, each of which is carried out under different environmental conditions to simulate various situations that may be encountered in actual production.

[0130] Firstly, the SVR model was used to predict the change values ​​of environmental parameters in the next stage, and the formula ratio of oyster peptide health products was adjusted accordingly.

[0131] Next, according to the adjusted formula ratio, the batching system accurately weighs various raw materials and sends them to the mixer for uniform mixing, and then to the granulator. During the granulation process, the temperature and humidity of the raw materials are monitored in real time, the environmental impact degree E is calculated, and the working parameters of the granulator are adjusted according to the E value.

[0132] Secondly, the initial particles are collected through a high-resolution camera to collect image data. The central control system uses the CNN model to extract particle features, calculate the quality index Q of the particles, and adjust the working parameters of the granulator again according to the Q value to optimize the particle quality.

[0133] Finally, the initial humidity of the optimized particles is monitored by a humidity sensor. The central control system selects the appropriate drying mode based on the humidity deviation, packages them after the drying process is completed, and generates a quality report.

[0134] The details are shown in Table 1 below:

[0135] Table 1 Comparison of production environment and particle quality

[0136]

[0137]

[0138] Through the analysis of the above experimental data, it can be clearly seen that with the increase of ambient temperature and humidity, the formula adjustment coefficient k also increases. This shows that under higher environmental conditions, in order to maintain the high quality of the product, greater adjustments are needed to cope with the impact of environmental changes on the production process. Specifically, when the ambient temperature rises from 22°C to 32°C and the ambient humidity increases from 50% to 70%, the formula adjustment coefficient k increases from 0.05 to 0.12. This trend of change reflects the important impact of environmental factors on the production process and also proves the effect of dynamically adjusting the formula ratio.

[0139] As the initial humidity of the pellets increases, the selected drying mode gradually changes from primary drying to tertiary drying. This shows that the central control system can flexibly select the most appropriate drying mode according to the actual humidity of the pellets, which not only ensures the drying efficiency but also avoids product quality problems caused by over-drying. For example, in stage 1, due to the low initial humidity of the pellets, the mild primary drying mode is selected, while in stage 3, due to the high initial humidity of the pellets, the efficient tertiary drying mode is selected.

[0140] In summary, the technical solution provided by the present invention not only effectively overcomes the problems of poor environmental adaptability and unstable product quality existing in traditional production methods by real-time monitoring of environmental parameters, dynamic adjustment of formula ratios, intelligent optimization of particle production and reasonable selection of drying modes, but also significantly improves production efficiency and consistency of product quality.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent processing control method for the production and granulation of oyster peptide health products, characterized in that: include, Environmental sensors are used to detect environmental parameters in real time, support vector regression (SVR) is used to identify the change values ​​of environmental parameters, and preset formula adjustment rules are used to dynamically adjust the formula ratio of oyster peptide health products; According to the adjusted formula ratio, the weighed raw materials are evenly mixed and sent to the granulator, the working parameters of the granulator are preliminarily adjusted according to the raw material data, and the initial granules are produced; Use deep learning models to extract initial particle features, calculate particle quality indicators, adjust the working parameters of the pelletizer based on the particle quality indicators, and optimize the quality of the initial particles; Monitoring the initial humidity data of the optimized particles, the central control system dynamically selects a drying mode according to the initial humidity data, so that the selected drying mode instruction is sent to the drying equipment, the drying process is started, and the moisture in the optimized particles is removed; Package the dried particles and generate a quality report for oyster peptide health products; The environmental parameters are detected in real time by environmental sensors, support vector regression (SVR) is used to identify the change values ​​of environmental parameters, and the formula ratio of oyster peptide health products is dynamically adjusted according to the initial formula adjustment rules. The specific steps are as follows: Deploy high-precision temperature sensors and humidity sensors at the production site to collect environmental parameters in real time, including temperature data and humidity data; The environmental parameters are transmitted to the central control system through IoT, and the central control system uses SVR to identify the change value of the environmental parameters; Based on the change value of environmental parameters, the preset formula adjustment rules are used to dynamically adjust the formula ratio of oyster peptide health products. The expression is: Among them, NR is the adjusted formula ratio, BR is the base formula ratio, k is the formula adjustment coefficient, ΔT h is the ambient temperature change, T h is the ambient temperature reference value, ΔH h is the change in ambient humidity, H h It is the reference value of the reference ambient humidity.

2. The intelligent processing control method for producing granulation of oyster peptide health products according to claim 1, characterized in that: According to the adjusted formula ratio, the weighed raw materials are evenly mixed and then fed into a granulator, the working parameters of the granulator are preliminarily adjusted according to the raw material data, and initial granules are produced. The specific steps are as follows: The adjusted formula ratio NR is transmitted to the batching system through the Internet of Things. The batching system accurately weighs the raw materials according to the adjusted formula, and sends the weighed raw materials to the mixer for uniform mixing and then to the granulator; The raw material data is monitored in real time through the sensors on the granulator, and transmitted to the central control system through IoT; the raw material data includes: raw material temperature and raw material humidity; The central control system evaluates the influence of raw material data on particle production by quantifying the deviation of data relative to the reference value, which is expressed as: Among them, E is the influence of raw material data on particle production, T m is the raw material temperature, T r is the raw material temperature reference value, H m is the raw material humidity, H r It is the reference value of raw material humidity; Define an environmental impact threshold E based on historical data and process requirements td , according to the influence degree E of raw material data on granule production, preliminarily adjust the working parameters of the granulator; When E≤E td When the temperature and humidity of the raw materials affect the pellet production, it means that the influence of the current raw material temperature and humidity data on the pellet production is within the safe range, and there is no need to adjust the working parameters of the pelletizer. When E>E td When the temperature and humidity of the current raw materials affect the pellet production beyond the safe range, the working parameters of the pellet mill need to be adjusted; the working parameters of the pellet mill include: the pressure, speed, heating intensity and shear force applied by the pellet mill; The granulator performs preliminary granulation according to the adjusted working parameters to form initial granules.

3. The intelligent processing control method for producing granulation of oyster peptide health products according to claim 2, characterized in that: The deep learning model is used to extract initial particle features and calculate the quality index of particles. The specific steps are as follows: The high-resolution camera on the pelletizer collects the image data of the initial pellets in real time and transmits the image data to the central control system through IoT technology; The central control system uses the input layer of the deep learning model to receive the image data of the initial particles, and extracts the particle features through the convolution layer. The particle features are reduced in feature dimension through the pooling layer, and then the global particle features are integrated through the fully connected layer, and Dropout is used to prevent overfitting. The deep learning model includes the input layer, convolution layer, pooling layer and fully connected layer. Particle characteristics include: average particle size, regularity of shape, and degree of surface defects; Based on the particle features extracted by the deep learning model, the quality index of the particles is calculated, and the expression is: Where S represents the average size of the particles, S i represents the ideal particle size, λ1 is the particle size difference adjustment factor, D(S) represents the regularity of particle shape, λ2 is the particle shape regularity adjustment factor, F(S) represents the degree of particle surface defects, λ3 is the particle surface defect adjustment factor, and Q is the quality index of the particle.

4. The intelligent processing control method for producing granulation of oyster peptide health products according to claim 3, characterized in that: The specific steps of adjusting the working parameters of the granulator according to the quality index of the granules and optimizing the quality of the initial granules are as follows: Define a particle quality standard threshold Q based on historical data and process requirements th , according to the quality index Q of the particles, adjust the working parameters of the granulator again; When Q ≥ Q th When , the current particle quality is considered qualified; When Q < Q th When , the current particle quality is considered unqualified; When the particle quality is unqualified, calculate the particle quality index Q and the particle quality standard threshold Q th According to the calculated difference, the working parameters of the granulator are adjusted again; The pelletizer optimizes the quality of the initial pellets according to the latest operating parameters.

5. The intelligent processing control method for granulation of oyster peptide health products according to claim 4, characterized in that: The monitoring optimizes the initial humidity data of the particles, and the central control system dynamically selects the drying mode according to the initial humidity data. The specific steps are as follows: The high-precision humidity sensor at the exit of the granulator monitors the initial humidity data of the optimized granules in real time, and transmits the initial humidity data collected by the humidity sensor to the central control system through IoT technology; The central control system calculates the deviation between the initial humidity data of the optimized particles and the humidity of the particles in the production standard according to the received initial humidity data; According to the deviation value H between the initial humidity data of the optimized particles and the humidity of the particles in the production standard dev , dynamically select the drying mode; the drying modes include: primary drying, secondary drying and tertiary drying; Based on historical data and process requirements, a low humidity deviation threshold H is defined. low and high humidity deviation threshold H high ; When H dev ≤H low When drying, select the first-level drying mode; When H low <H dev ≤H high When the air is in the hot zone, select the secondary drying mode; When H dev >H high When drying, select the three-level drying mode; The central control system sends the selected drying mode command to the drying equipment, starting the drying process to remove moisture from the optimized particles.

6. The intelligent processing control method for granulation of oyster peptide health products according to claim 5, characterized in that: The dried particles are packaged and a quality report of oyster peptide health products is generated. The specific steps are as follows: After the drying process is completed, the dried particles are transferred from the drying equipment to the packaging area by a conveyor belt; In the packaging area, high-precision weighing equipment is used to weigh the dried particles, and an automatic packaging machine is used to seal and package the weighed particles; After packaging is completed, the central control system records the quality indicators of the current batch of particles, and generates a quality report for the current batch of oyster peptide health products based on the quality indicators of the current batch.

7. An intelligent processing control system for the production and granulation of oyster peptide health products, characterized in that: It includes: environmental parameter monitoring and formula adjustment module, granulator parameter preliminary adjustment module, initial granule quality optimization module, granule drying module and granule packaging and quality report generation module; Environmental parameter monitoring and formula adjustment module: used to detect environmental parameters in real time through environmental sensors, use support vector regression SVR to identify environmental parameter change values, and use preset formula adjustment rules to dynamically adjust the formula ratio of oyster peptide health products; Granulator parameter preliminary adjustment module: used to evenly mix the weighed raw materials according to the adjusted formula ratio and then feed them into the granulator, preliminarily adjust the granulator's working parameters according to the raw material data, and make initial granules; Initial particle quality optimization module: used to extract initial particle features using a deep learning model, calculate particle quality indicators, adjust the working parameters of the pelletizer according to the particle quality indicators, and optimize the quality of the initial particles; Granule drying module: used to monitor the initial humidity data of the optimized granules. The central control system dynamically selects the drying mode according to the initial humidity data, so that the selected drying mode instruction is sent to the drying equipment to start the drying process and remove the moisture in the optimized granules. Granule packaging and quality report generation module: used to package the dried granules and generate the oyster peptide health product quality report.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent processing control method for the production and granulation of oyster peptide health products according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent processing control method for the production and granulation of oyster peptide health products according to any one of claims 1 to 6 are implemented.

Images